Foke Singh a811b2e1e3 llama: fix dimensions and data types ... Removed unnecessary batching dimension introduced by recent changes. Converted index outputs from i32 to u32 for token indices. Ensures Llama runs on CUDA and RoCM. Tested on CUDA.		2024-03-20 13:37:19 +00:00
..
BUILD.bazel	Update Llama example docs and Bazel build files, and add tests for the new HuggingFace tokenizer integration.	2024-03-04 12:11:13 +00:00
llama.zig	llama: fix dimensions and data types	2024-03-20 13:37:19 +00:00
main.zig	llama: fix dimensions and data types	2024-03-20 13:37:19 +00:00
test_tokenizer.zig	Add Bazel build rule and test for Llama3 tokenizer’s byte fallback and unknown token handling.	2024-02-02 10:25:48 +00:00
test.zig	Update Llama example docs and Bazel build files, and add tests for the new HuggingFace tokenizer integration.	2024-03-04 12:11:13 +00:00